Real Time Semantic Segmentation On Cityscapes 1

Metriken

mIoU

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	mIoU	Paper Title	Repository
PP-LiteSeg-T1	73.1	PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
SegNext-T-Seg100	79.8%	SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation
DSNet	80.4%	DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation
RTFormer-S	76.3%	RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
PIDNet-M	79.9%	PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
DDRNet23-slim	77.4	Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
DDRNet23	79.4	Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
PIDNet-S	78.8%	PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
CSFNet-1	74.73	CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes	-
RTFormer-B	79.3%	RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
LiteSeg-MobileNet	67.8%	LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation
FasterSeg	73.1	FasterSeg: Searching for Faster Real-time Semantic Segmentation
PIDNet-L	80.9%	PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
BiseNetV2-L	75.8%	BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
CSFNet-2	76.36	CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes	-
PP-LiteSeg-B2	78.2	PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
SwiftNetRN-18	75.5%	In defence of metric learning for speaker recognition
BiseNetV2	73.5%	BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
PP-LiteSeg-T2	76	PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
Mobile-Seed	78.4%	Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots

0 of 24 row(s) selected.